analyze-trace — Agent Trace Check MCP Prompt
analyze-trace
is one of 1 prompt on the
Agent Trace Check
MCP server. Connect the server and it appears in your client, ready to invoke.
by client
How to invoke analyze-trace from your client
- Claude Code Agent Trace Check Prompt/analyze-trace run in your project directory
- Claude Desktop Agent Trace Check Prompt/analyze-trace ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Agent Trace Check Prompt/analyze-trace ~/.cursor/mcp.json
- VS Code Agent Trace Check Prompt/analyze-trace .vscode/mcp.json
- Zed Agent Trace Check Prompt/analyze-trace ~/.config/zed/settings.json
- Windsurf Agent Trace Check Prompt/analyze-trace ~/.codeium/windsurf/mcp_config.json
- Cline Agent Trace Check Prompt/analyze-trace ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Agent Trace Check Prompt/analyze-trace ~/.gemini/settings.json
- Grok Agent Trace Check Prompt/analyze-trace .mcp.json (in your project root)
- ChatGPT Agent Trace Check Prompt/analyze-trace Settings → Connectors → Advanced → Developer mode
- Claude.ai Agent Trace Check Prompt/analyze-trace Settings → Connectors → Add custom connector
- LangChain Agent Trace Check Prompt/analyze-trace pip install langchain-mcp-adapters
Read from the server itself, by connecting to it and calling prompts/list on 14 November 2026.
A listing does not declare its prompts, so asking is the only way to know them, and this
is what the server actually offers rather than what its listing claims. Names only are
stored; connect the server for each prompt's arguments.